Universities all around the world operate by following several institutional missions, with a central purpose on teaching and research activities. The importance of each aspect alongside the connection between them provide a disputed topic in the literature, many authors confirming or rejecting the intuitive inverse relationship by using various means, more or less quantitative. This paper aims to examine the teaching and research dimensions of the research-active European universities from a data mining perspective. For each dimension previously considered we employ the K-means Clustering in order to identify the groups of similar higher education institutions and we analyze the insights produced by the results. In addition, we build some target variables considering the teaching and research outputs and we investigate their drivers by employing the Logistic Regression. Furthermore, we explore the controverted relationship between the two institutional missions we considered through the use of Correspondence Analysis. Preliminary results illustrate that the dataset contains two types of universities: a category of very large and prestigious institutions and a second group of small and medium sized institutions, quite different from each other. Interest insights are given by the third part of the study, in which the Correspondence Analysis confirms an inverse relationship between teaching and research activities. Unfortunately, this is very likely a consequence of the time constraint – both activities require the same limited resources and therefore increasing the teaching burden for academics may diminish the time and energy dedicated to research.
If the inline PDF is not rendering correctly, you can download the PDF file here.
Bonaccorsi, A., Daraio, C., Simar, L. (2006). Advanced indicators of productivity of universities. An application of robust nonparametric methods to Italian data. Scientometrics, 66(2), 389-410.
Cabrera, J.C., Karl, S.R., Rodriguez, M.C. (2019). Predicting College Enrollment for Students Who Partake in Music or Dance Lessons Using Propensity Score Matching and Logistic Regression. Paper presented at the annual meeting of the American Educational Research Association, Toronto, Canada.
Calderini, M., Franzoni, C. (2004). Is academic patenting detrimental to high quality research? An empirical analysis of the relationship between scientific careers and patent applications. Paper presented to the 4th workshop on Economic Transformation in Europe, Sophia Antipolis, January 29-30, 2004.
Daraio, C., Bonaccorsi, A., Simar, L. (2015). Rankings and university performance: A conditional multidimensional approach. European Journal of Operational Research, 244(3), 918-930.
Doey, L., Kurta, J. (2011). Correspondence Analysis applied to psychological research. Tutorials in Quantitative Methods for Psychology, 7(1), 5-14.
Gray, P., Froh, R., Diamond, R. (1992). A National Study of Research Universities: On the Balance between Research and Undergraduate Teaching. Center for Instructional Development, Syracuse University.
Hastie, T., Tibshirani, R., Friedman, J. (2017). The Elements of Statistical Learning. Data Mining, Inference and Prediction. Second edition, Springer.
Hattie, J., Marsh H.W. (1996). The relationship between teaching and research: A meta-analysis. Review of Educational Research, 66(4), 507-542.
Hoffman, D., Franke, G. (1986). Correspondence Analysis: Graphical Representation of Categorical Data in Marketing Research. Journal of Marketing Research, 23(3), 213-227.
James, G., Witten, D., Hastie, T., Tibshirani, R. (2013). An Introduction to Statistical Learning with Applications in R. New York, Springer.
Maer Matei, M.M. (2018). Analiza datelor cu R. Editura Universitara, Bucuresti.
Stoica, M., Aldea, A. (2016). Efficiency of teaching and research activities in Romanian universities: An order-alpha partial frontiers approach. Economic Computation and Economic Cybernetics Studies and Research, 50(4), 169-186.
Westgaard, S., Wijst, N. (2001). Default probabilities in a corporate bank portfolio: A logistic model approach. European Journal of Operational Research, 135(2), 338-349.